Membership Inference for Contrastive Pre-training Models with Text-only PII Queries

Documenti analoghi

• Five Queries Are Enough: Query-Efficient and Surrogate-Free Membership Inference Attacks on RAG via Entailment
  di: Nguyen, Nguyen Linh Bao, et al.
  Pubblicazione: (2026)
• Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
  di: Wen, Yuxin, et al.
  Pubblicazione: (2024)
• Membership Information Leakage in Federated Contrastive Learning
  di: Chen, Kongyang, et al.
  Pubblicazione: (2024)
• WebPII: Benchmarking Visual PII Detection for Computer-Use Agents
  di: Zhao, Nathan
  Pubblicazione: (2026)
• Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models
  di: He, Yu, et al.
  Pubblicazione: (2025)